convnext-base-224

Model overview

convnext-base-224 is published by Facebook as an image-classification model with ConvNextForImageClassification architecture and a convnext model type. According to the model card, it is a base-sized ConvNeXt model trained on ImageNet-1k at 224x224, introduced in the paper A ConvNet for the 2020s. Captured metadata records an Apache-2.0 license and Transformers library compatibility.

Recorded capabilities

Use cases in the source record

• Raw image classification of photographs, such as COCO 2017 images, into one of the 1,000 ImageNet classes.
• Exploring fine-tuned versions on the model hub for tasks beyond raw classification, as suggested by the model card.

Limitations and unknowns

• No parameter count was extracted from this record.
• No evaluation results were extracted from this record.
• Provider state is historical snapshot data, not independently refreshed current availability.
• The model card was written by the Hugging Face team, not the original releasing team, and its claims have not been independently verified by Ethen.

Source and provenance

Source: facebook/convnext-base-224

Captured: Unknown. Processed: 2026-09-07T19:34:44.356099+00:00.

ConvNeXT (base-sized model) ConvNeXT model trained on ImageNet-1k at resolution 224x224. It was introduced in the paper A ConvNet for the 2020s by Liu et al. and first released in this repository . Disclaimer: The team releasing ConvNeXT did not write a model card for this model so this model card has been written by the Hugging Face team. Model description ConvNeXT is a pure convolutional model (ConvNet), inspired by the design of Vision Transformers, that claims to outperform them. The authors started from a ResNet and "modernized" its design by taking the Swin Transformer as inspiration. Intended uses & limitations You can use th…